Coastal farmland irrigation management method and device based on intelligent agricultural control gateway

Abstract

The invention discloses a coastal farmland irrigation management method and device based on an intelligent agricultural control gateway, and the method comprises the steps: carrying out the linear regression analysis of historical underground water level data and historical tide data, and building a tidal power model according to an analysis result; training an initial crop growth model constructed in the farmland of the target coastal region based on the historical soil data, the historical meteorological data and the historical underground water level data to obtain a trained crop growth model; in the irrigation management process of the target coastal region farmland, inputting real-time tide data into a tidal power model to obtain real-time underground water level data, and inputting the real-time underground water level data, real-time soil data and real-time meteorological data into a crop growth model to obtain growth prediction indexes of crops in the target coastal region farmland; and controlling the intelligent agricultural control gateway to execute an irrigation plan matched with the growth prediction index. According to the method provided by the invention, the irrigation management optimization of the coastal farmland is realized.

Description

Technical Field

[0001] The present application relates to the field of automatic irrigation technology, and in particular to a coastal farmland irrigation management method and device based on a smart agriculture control gateway. Background Art

[0002] With the acceleration of urbanization, the inland cultivated land area is gradually decreasing. Urbanization occupies a large amount of farmland, especially high-quality cultivated land resources. Therefore, coastal areas have become a new area for agricultural development. In particular, some coastal countries and regions have increased agricultural production areas through the development of marine resources and the improvement of saline-alkali land. Due to the special geographical and climatic conditions of coastal areas, agricultural production in these areas faces some unique challenges.

[0003] Traditional agricultural automatic irrigation systems can only work according to fixed irrigation strategies, without considering that coastal farmland is affected by multiple factors, and therefore cannot respond to sudden changes in the actual water demand of crops in real time. This can lead to insufficient irrigation when crops need water the most, or unnecessary irrigation when the soil is already sufficiently moist.

[0004] It can be seen that how to optimize the technical problem of irrigation management of coastal farmland has become a technical problem that needs to be urgently solved by technical personnel in this field. Summary of the invention

[0005] The present application provides a coastal farmland irrigation management method and device based on a smart agriculture control gateway to solve the technical problem of how to optimize coastal farmland irrigation management.

[0006] In order to solve the above technical problems, the embodiment of the present application provides a coastal farmland irrigation management method based on a smart agriculture control gateway, including:

[0007] Obtain historical soil data, historical groundwater level data, historical meteorological data, and historical tidal data of farmland in the target coastal area respectively;

[0008] Performing linear regression analysis on the historical groundwater level data and the historical tidal data, and establishing a tidal force model according to the analysis results;

[0009] Training an initial crop growth model constructed in the farmland in the target coastal area based on the historical soil data, the historical meteorological data, and the historical groundwater level data to obtain a trained crop growth model;

[0010] In the process of irrigation management of the farmland in the target coastal area, the acquired real-time tidal data is input into the tidal force model to obtain real-time groundwater level data, and the real-time groundwater level data, the acquired real-time soil data and real-time meteorological data are input into the crop growth model to obtain growth prediction indicators of crops in the farmland in the target coastal area;

[0011] Control the smart agriculture control gateway to execute an irrigation plan that matches the growth prediction index.

[0012] As one of the preferred solutions, the linear regression analysis is performed on the historical groundwater level data and the historical tidal data, and a tidal force model is established according to the analysis results, including:

[0013] Preprocessing the acquired historical groundwater level data and the historical tidal data;

[0014] Draw a scatter plot based on the preprocessed historical groundwater level data and the historical tidal data, and obtain the correlation between the historical groundwater level data and the historical tidal data based on the scatter plot;

[0015] An initial tidal force model is constructed according to the correlation, and the initial tidal force model is optimized by using the historical groundwater level data and the historical tidal data to obtain an optimized tidal force model.

[0016] As one preferred solution, the initial crop growth model constructed in the farmland in the target coastal area is trained based on the historical soil data, the historical meteorological data and the historical groundwater level data to obtain a trained crop growth model, including:

[0017] Construct an initial crop growth model based on long short-term memory network;

[0018] Preprocessing the historical soil data, the historical meteorological data, and the historical groundwater level data to obtain a training data set;

[0019] The initial crop growth model is iteratively trained according to the training data set, and during the training process, the model parameters of the initial crop growth model are optimized by a back propagation algorithm to obtain a trained crop growth model.

[0020] As one of the preferred solutions, the historical soil data, the historical meteorological data and the historical groundwater level data are preprocessed to obtain a training data set, including:

[0021] Performing time alignment processing on the historical soil data, the historical meteorological data and the historical groundwater level data to obtain an initial data set;

[0022] Extracting features from the initial data set to obtain target feature data, wherein the target features include soil moisture, soil temperature, precipitation, light intensity, and groundwater level;

[0023] The target feature data is standardized to obtain the training data set.

[0024] As one preferred solution, the growth prediction index includes crop water stress index, crop growth rate, soil moisture content, comprehensive index of meteorological conditions and crop growth stage;

[0025] The control smart agriculture control gateway executes an irrigation plan that matches the growth prediction index, including:

[0026] Determining the irrigation amount of the target coastal area farmland according to the crop water stress index, the crop growth rate and the soil moisture content;

[0027] Determine the irrigation time of the farmland in the target coastal area according to the comprehensive index of meteorological conditions;

[0028] determining the frequency and duration of irrigation according to the growth stage of the crop;

[0029] An irrigation calculation is formulated based on the irrigation amount, the irrigation time, the irrigation frequency and the irrigation duration, and the smart agriculture control gateway is controlled to execute the irrigation plan.

[0030] Another embodiment of the present application provides a coastal farmland irrigation management device based on a smart agriculture control gateway, comprising:

[0031] An acquisition module is used to respectively acquire historical soil data, historical groundwater level data, historical meteorological data, and historical tidal data of farmland in the target coastal area;

[0032] An analysis module, used for performing linear regression analysis on the historical groundwater level data and the historical tidal data, and establishing a tidal force model according to the analysis results;

[0033] A training module, used for training the initial crop growth model constructed in the farmland in the target coastal area based on the historical soil data, the historical meteorological data and the historical groundwater level data to obtain a trained crop growth model;

[0034] A prediction module, used for inputting the acquired real-time tidal data into the tidal force model to obtain real-time groundwater level data during the irrigation management of the farmland in the target coastal area, and inputting the real-time groundwater level data, the acquired real-time soil data and the real-time meteorological data into the crop growth model to obtain growth prediction indicators of crops in the farmland in the target coastal area;

[0035] The irrigation module is used to control the smart agriculture control gateway to execute an irrigation plan that matches the growth prediction index.

[0036] As one preferred solution, the analysis module is specifically used for:

[0037] Preprocessing the acquired historical groundwater level data and the historical tidal data;

[0038] Draw a scatter plot based on the preprocessed historical groundwater level data and the historical tidal data, and obtain the correlation between the historical groundwater level data and the historical tidal data based on the scatter plot;

[0039] An initial tidal force model is constructed according to the correlation, and the initial tidal force model is optimized by using the historical groundwater level data and the historical tidal data to obtain an optimized tidal force model.

[0040] As one preferred solution, the training module is specifically used for:

[0041] Construct an initial crop growth model based on long short-term memory network;

[0042] Preprocessing the historical soil data, the historical meteorological data, and the historical groundwater level data to obtain a training data set;

[0043] The initial crop growth model is iteratively trained according to the training data set, and during the training process, the model parameters of the initial crop growth model are optimized by a back propagation algorithm to obtain a trained crop growth model.

[0044] As one preferred solution, the training module is further used for:

[0045] Performing time alignment processing on the historical soil data, the historical meteorological data and the historical groundwater level data to obtain an initial data set;

[0046] Extracting features from the initial data set to obtain target feature data, wherein the target features include soil moisture, soil temperature, precipitation, light intensity, and groundwater level;

[0047] The target feature data is standardized to obtain the training data set.

[0048] As one preferred solution, the growth prediction index includes crop water stress index, crop growth rate, soil moisture content, comprehensive index of meteorological conditions and crop growth stage;

[0049] The irrigation module is specifically used for:

[0050] Determining the irrigation amount of the target coastal area farmland according to the crop water stress index, the crop growth rate and the soil moisture content;

[0051] Determine the irrigation time of the farmland in the target coastal area according to the comprehensive index of meteorological conditions;

[0052] determining the frequency and duration of irrigation according to the growth stage of the crop;

[0053] An irrigation calculation is formulated based on the irrigation amount, the irrigation time, the irrigation frequency and the irrigation duration, and the smart agriculture control gateway is controlled to execute the irrigation plan.

[0054] Compared with the prior art, the beneficial effects of the embodiments of the present application are at least one of the following:

[0055] 1) The tidal force model constructed in this application can predict the trend of groundwater level changes with tides, which is crucial for coastal farmland. Because tidal changes will directly affect the groundwater level, which in turn affects the irrigation needs and soil moisture conditions of farmland. Through model prediction, irrigation plans can be adjusted in advance to avoid over- or under-irrigation.

[0056] 2) The crop growth model constructed in this application can predict the growth status of crops based on real-time data. This helps to understand the growth requirements of crops under different environmental conditions, so as to formulate more scientific and reasonable irrigation plans. At the same time, the model parameters can be continuously optimized during the model training process to improve the accuracy of the prediction.

[0057] 3) This application enables irrigation management to respond quickly to changes in the farmland environment through the input of real-time data and the output of prediction results. The irrigation plan formulated according to the crop growth results is more in line with the actual needs of the crops, which helps to improve irrigation efficiency and crop yields. At the same time, real-time management also reduces the frequency and intensity of manual intervention and reduces management costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 It is a flow chart of a coastal farmland irrigation management method based on a smart agriculture control gateway in one embodiment of the present application;

[0059] Figure 2This is an overall architecture diagram of a smart agriculture control gateway system in one embodiment of the present application;

[0060] Figure 3 It is a structural diagram of a coastal farmland irrigation management device based on a smart agriculture control gateway in one of the embodiments of the present application. DETAILED DESCRIPTION

[0061] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. The purpose of providing these embodiments is to make the disclosure of the present application more thorough and comprehensive. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0062] In the description of this application, the terms "first", "second", "third", etc. are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first", "second", "third", etc. may explicitly or implicitly include one or more of the feature. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0063] In the description of the present application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be a connection between the two elements. The terms "vertical", "horizontal", "left", "right", "upper", "lower" and similar expressions used in this article are only for illustrative purposes, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on this application. The term "and / or" used in this article includes any and all combinations of one or more related listed items. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0064] In the description of this application, it should be noted that, unless otherwise defined, all technical and scientific terms used in this application have the same meaning as those commonly understood by those skilled in the art. The terms used in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood by specific circumstances.

[0065] An embodiment of the present application provides a coastal farmland irrigation management method based on a smart agriculture control gateway. For details, please refer to Figure 1 , Figure 1 The flowchart of the coastal farmland irrigation management method based on the smart agriculture control gateway in one embodiment of the present application is shown, which includes steps S1-S5:

[0066] S1: Obtain historical soil data, historical groundwater level data, historical meteorological data, and historical tidal data of farmland in the target coastal area respectively;

[0067] In this step, soil sensors, meteorological sensors, groundwater observation systems, and tidal observation systems are used to obtain historical soil data, historical groundwater level data, historical meteorological data, and historical tidal data of farmland in the target coastal area. In one embodiment of the present application, relevant data can be obtained from soil databases, meteorological data platforms, and scientific research institutions in the target coastal area.

[0068] S2: Conduct linear regression analysis on historical groundwater level data and historical tide data, and establish a tidal force model based on the analysis results;

[0069] Preferably, in one embodiment of the present application, a linear regression analysis is performed on historical groundwater level data and historical tidal data, and a tidal force model is established according to the analysis results, including:

[0070] Pre-process the acquired historical groundwater level data and historical tide data;

[0071] Draw a scatter plot based on the pre-processed historical groundwater level data and historical tide data, and obtain the correlation between the historical groundwater level data and the historical tide data based on the scatter plot;

[0072] An initial tidal force model is constructed according to the correlation, and the initial tidal force model is optimized through historical groundwater level data and historical tidal data to obtain an optimized tidal force model.

[0073] Specifically, the historical groundwater level data and historical tidal data are preprocessed, including removing missing values, outlier processing and time alignment. Among them, removing missing values ​​includes checking the historical groundwater level data and historical tidal data, and removing or filling missing data points. Outlier processing includes identifying and processing outliers in the data, which may be caused by measurement errors or equipment failures. Time alignment includes ensuring that the historical groundwater level data and historical tidal data are aligned in time, that is, the data at each time point are corresponding.

[0074] In one embodiment of the present application, if the dimensions of the groundwater level data and the tide data are different after preprocessing (for example, the groundwater level is in meters and the tide is in centimeters), standardization is required. Standardization can be achieved by converting the data into Z scores (i.e., standard scores of the data) or performing minimum-maximum scaling.

[0075] Before performing linear regression analysis, a scatter plot is drawn using the preprocessed historical groundwater level data and historical tide data. It can be understood that a scatter plot can intuitively display the relationship between two variables, including positive correlation, negative correlation, or irrelevance. By observing the scatter plot, it can be determined whether there is a linear relationship between the historical groundwater level data and the historical tide data, and a correlation coefficient (such as the Pearson correlation coefficient) can be used to quantify the strength and direction of the linear relationship between the two variables.

[0076] According to the scatter plot and correlation coefficient, a linear regression model is assumed as the initial tidal force model, and the preprocessed historical groundwater level data and historical tidal data are used to train the initial tidal force model. Specifically, the least squares method or other optimization algorithms can be used to estimate the parameters of the model, and a part of the historical data that is not involved in the model training can be used to verify the performance of the model, and finally a tidal force model for predicting future groundwater level changes can be obtained.

[0077] S3: Training the initial crop growth model constructed in the farmland of the target coastal area based on historical soil data, historical meteorological data and historical groundwater level data to obtain a trained crop growth model;

[0078] Preferably, in one embodiment of the present application, the initial crop growth model constructed in the farmland of the target coastal area is trained based on historical soil data, historical meteorological data and historical groundwater level data to obtain a trained crop growth model, including:

[0079] Construct an initial crop growth model based on long short-term memory network;

[0080] Preprocess historical soil data, historical meteorological data, and historical groundwater level data to obtain a training data set;

[0081] The initial crop growth model is iteratively trained according to the training data set, and during the training process, the model parameters of the initial crop growth model are optimized by a back propagation algorithm to obtain a trained crop growth model.

[0082] In this step, the long short-term memory network (LSTM) is selected as the architecture of the initial crop growth model. LSTM is a special recurrent neural network (RNN) that can capture long-term dependencies in time series data and is very suitable for processes such as crop growth that have temporal continuity and periodic changes. Design the input layer, hidden layer, and output layer of the LSTM model. The input layer receives preprocessed soil data, meteorological data, and groundwater level data; the hidden layer contains multiple LSTM units to capture the temporal dependencies in the data; and the output layer outputs relevant indicators of crop growth.

[0083] Before model training, data needs to be preprocessed.

[0084] Preferably, in one embodiment of the present application, historical soil data, historical meteorological data and historical groundwater level data are preprocessed to obtain a training data set, including:

[0085] Perform time alignment processing on historical soil data, historical meteorological data and historical groundwater level data to obtain the initial data set;

[0086] Extract features from the initial data set to obtain target feature data, including soil moisture, soil temperature, precipitation, light intensity, and groundwater level;

[0087] The target feature data is standardized to obtain the training data set.

[0088] Specifically, check the timestamps of all data to ensure that they are aligned on the same time scale (such as day, hour, minute, etc.). If the timestamps do not match, you need to interpolate or discard some data points so that all data have corresponding observations at the same time point. In the process of time alignment, you will find that some time points are missing. For missing values, you can use interpolation methods (such as linear interpolation, nearest neighbor interpolation, etc.) to fill them, or decide whether to directly discard these time points based on the characteristics of the data and the severity of the missing.

[0089] Extract features that have an important impact on crop growth, including soil moisture, soil temperature, precipitation, light intensity, and groundwater level, and integrate the extracted features to form a data set containing target features. Since the dimensions and value ranges of different features may vary greatly, in order to eliminate the impact of such differences on model training, the target feature data needs to be standardized.

[0090] The standardized dataset is divided into training set, validation set and test set. The training set is used to train the model, the validation set is used to adjust the model parameters and prevent overfitting, and the test set is used to evaluate the final performance of the model.

[0091] In one embodiment of the present application, the initial crop growth model is iteratively trained using a training data set. In each iteration, the model predicts crop growth conditions based on input data, and the performance of the model is evaluated by calculating the error between the predicted value and the true value.

[0092] The parameters of the model are optimized using a back propagation algorithm. The back propagation algorithm minimizes the loss function and improves the performance of the model by calculating the gradient of the loss function to the model parameters and updating the parameters in the opposite direction of the gradient. During the training process, the hyperparameters of the model, such as the learning rate, batch size, number of LSTM units, etc., are adjusted according to the performance of the validation set to optimize the performance of the model. In one embodiment of the present application, an early stopping method is used to prevent the model from overfitting. When the performance of the validation set does not improve in multiple consecutive iterations, the training is stopped and the current optimal model parameters are saved.

[0093] S4: In the process of irrigation management of farmland in the target coastal area, the acquired real-time tidal data is input into the tidal force model to obtain the real-time groundwater level data, and the real-time groundwater level data, the acquired real-time soil data and the real-time meteorological data are input into the crop growth model to obtain the growth prediction index of the crops in the farmland in the target coastal area;

[0094] Specifically, the tidal force model obtained in step 2 calculates the real-time groundwater level prediction value, i.e., the real-time groundwater level data, based on the real-time tidal data. The real-time groundwater level data, the real-time soil data, and the real-time meteorological data are integrated together to form a complete real-time data set.

[0095] The integrated real-time data set is input into the crop growth model of step 3. The crop growth model calculates the crop growth prediction index based on the input real-time data set. In one embodiment of the present application, the growth prediction index includes the crop water stress index, the crop growth rate, the soil moisture content, the comprehensive index of meteorological conditions and the crop growth stage.

[0096] S5: Control the smart agriculture control gateway to execute an irrigation plan that matches the growth prediction indicators.

[0097] The control gateway of smart agriculture is a highly integrated system. Figure 2 As shown, Figure 2 The overall architecture diagram of a smart agricultural control gateway system provided in the embodiment of the present application realizes the precision and efficiency of agricultural irrigation through the coordinated work of multiple parts such as the sensor network irrigation control system, cloud platform communication system, tidal system and weather forecast system interface. It can not only improve the utilization efficiency of water resources, but also reduce the use of fertilizers and pesticides, reduce the pollution of agricultural production to the environment, and promote the development of agriculture towards green and intelligent directions.

[0098] The control smart agriculture control gateway is the core program of the entire gateway system. It integrates the operating system, communication protocol stack, AI algorithm library, etc. It is responsible for receiving sensor data, preprocessing, feature extraction and model reasoning, and finally generating irrigation decisions. It is also responsible for connecting with the interface of the weather forecast system and the tidal prediction platform interface to obtain the latest weather information and lunar tidal data, and combines sensor data and historical irrigation records to predict future irrigation needs through machine learning or deep learning algorithms, and formulate accurate irrigation plans. The sensor acquisition program is responsible for monitoring the environmental parameters in the farmland, including soil moisture, temperature, light intensity and rainfall, etc. The collected data is transmitted to the control smart agriculture control gateway as the basis for irrigation control. The irrigation control program is responsible for controlling the operation of irrigation equipment such as water pumps and valves based on the irrigation decisions generated by the AI ​​gateway. The cloud platform communication program realizes the access communication between the agricultural AI control gateway and the smart agriculture platform. The smart agriculture platform provides functions such as data storage, data analysis, remote monitoring and alarm, which can view farmland environmental parameters, irrigation plans and irrigation execution in real time, and can also be remotely controlled and adjusted as needed. The weather forecast interface program is a bridge between the AI ​​gateway and the weather forecast system. It is responsible for obtaining the latest weather information in real time, such as rainfall, temperature, humidity, etc., and providing necessary data support for the AI ​​gateway. The security management program is responsible for ensuring the security of data transmission and processing, preventing data leakage and illegal access, and includes security measures such as SM4 encryption, identity authentication mechanism and firewall.

[0099] Preferably, in one embodiment of the present application, controlling the smart agriculture control gateway to execute an irrigation plan that matches the growth prediction index includes:

[0100] Determine irrigation amounts for farmland in target coastal areas based on crop water stress index, crop growth rate, and soil moisture content;

[0101] Determine the irrigation time for farmland in the target coastal area based on the comprehensive index of meteorological conditions;

[0102] Determine irrigation frequency and duration according to crop growth stage;

[0103] Make irrigation calculations based on irrigation amount, irrigation time, irrigation frequency and irrigation duration, and control the smart agriculture control gateway to execute the irrigation plan.

[0104] During the irrigation process, the growth of crops and soil moisture data are continuously monitored, and the irrigation strategy is adjusted in time according to the actual situation. This can ensure that crops grow under the best growth conditions while avoiding the waste of water resources.

[0105] Compared with the prior art, the embodiments of the present application have the following advantages:

[0106] 1) The tidal force model constructed in this application can predict the trend of groundwater level changes with tides, which is crucial for coastal farmland. Because tidal changes will directly affect the groundwater level, which in turn affects the irrigation needs and soil moisture conditions of farmland. Through model prediction, irrigation plans can be adjusted in advance to avoid over- or under-irrigation.

[0107] 2) The crop growth model constructed in this application can predict the growth status of crops based on real-time data. This helps to understand the growth requirements of crops under different environmental conditions, so as to formulate more scientific and reasonable irrigation plans. At the same time, the model parameters can be continuously optimized during the model training process to improve the accuracy of the prediction.

[0108] 3) This application enables irrigation management to respond quickly to changes in the farmland environment through the input of real-time data and the output of prediction results. The irrigation plan formulated according to the crop growth results is more in line with the actual needs of the crops, which helps to improve irrigation efficiency and crop yields. At the same time, real-time management also reduces the frequency and intensity of manual intervention and reduces management costs.

[0109] Another embodiment of the present application provides a coastal farmland irrigation management method based on a smart agriculture control gateway. For details, please refer to Figure 3 , Figure 3 The structure diagram of a coastal farmland irrigation management device based on a smart agriculture control gateway in one embodiment of the present application is shown, which includes: an acquisition module 11, an analysis module 12, a training module 13, a prediction module 14, and an irrigation module 15, wherein:

[0110] An acquisition module 11 is used to respectively acquire historical soil data, historical groundwater level data, historical meteorological data and historical tidal data of farmland in a target coastal area;

[0111] An analysis module 12 is used to perform linear regression analysis on historical groundwater level data and historical tide data, and establish a tidal force model based on the analysis results;

[0112] A training module 13 is used to train the initial crop growth model constructed in the farmland of the target coastal area based on historical soil data, historical meteorological data and historical groundwater level data to obtain a trained crop growth model;

[0113] The prediction module 14 is used to input the acquired real-time tidal data into the tidal force model to obtain real-time groundwater level data during the irrigation management of the farmland in the target coastal area, and input the real-time groundwater level data, the acquired real-time soil data and the real-time meteorological data into the crop growth model to obtain the growth prediction index of the crops in the farmland in the target coastal area;

[0114] The irrigation module 15 is used to control the smart agriculture control gateway to execute an irrigation plan that matches the growth prediction index.

[0115] Preferably, in one embodiment of the present application, the analysis module is specifically used for:

[0116] Pre-process the acquired historical groundwater level data and historical tide data;

[0117] Draw a scatter plot based on the pre-processed historical groundwater level data and historical tide data, and obtain the correlation between the historical groundwater level data and the historical tide data based on the scatter plot;

[0118] An initial tidal force model is constructed according to the correlation, and the initial tidal force model is optimized through historical groundwater level data and historical tidal data to obtain an optimized tidal force model.

[0119] Preferably, in one embodiment of the present application, the training module is specifically used for:

[0120] Construct an initial crop growth model based on long short-term memory network;

[0121] Preprocess historical soil data, historical meteorological data, and historical groundwater level data to obtain a training data set;

[0122] The initial crop growth model is iteratively trained according to the training data set, and during the training process, the model parameters of the initial crop growth model are optimized by a back propagation algorithm to obtain a trained crop growth model.

[0123] Preferably, in one embodiment of the present application, the training module is further used for:

[0124] Perform time alignment processing on historical soil data, historical meteorological data and historical groundwater level data to obtain the initial data set;

[0125] Extract features from the initial data set to obtain target feature data, including soil moisture, soil temperature, precipitation, light intensity, and groundwater level;

[0126] The target feature data is standardized to obtain the training data set.

[0127] Preferably, in one embodiment of the present application, the growth prediction index includes a crop water stress index, a crop growth rate, soil moisture content, a comprehensive index of meteorological conditions, and a crop growth stage;

[0128] Irrigation modules, specifically for:

[0129] Determine irrigation amounts for farmland in target coastal areas based on crop water stress index, crop growth rate, and soil moisture content;

[0130] Determine the irrigation time for farmland in the target coastal area based on the comprehensive index of meteorological conditions;

[0131] Determine irrigation frequency and duration according to crop growth stage;

[0132] Make irrigation calculations based on irrigation amount, irrigation time, irrigation frequency and irrigation duration, and control the smart agriculture control gateway to execute the irrigation plan.

[0133] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A coastal farmland irrigation management method based on a smart agriculture control gateway, characterized in that: include: Obtain historical soil data, historical groundwater level data, historical meteorological data, and historical tidal data of farmland in the target coastal area respectively; Performing linear regression analysis on the historical groundwater level data and the historical tidal data, and establishing a tidal force model according to the analysis results; Training an initial crop growth model constructed in the farmland in the target coastal area based on the historical soil data, the historical meteorological data, and the historical groundwater level data to obtain a trained crop growth model; In the process of irrigation management of the farmland in the target coastal area, the acquired real-time tidal data is input into the tidal force model to obtain real-time groundwater level data, and the real-time groundwater level data, the acquired real-time soil data and real-time meteorological data are input into the crop growth model to obtain growth prediction indicators of crops in the farmland in the target coastal area; Control the smart agriculture control gateway to execute an irrigation plan that matches the growth prediction index.

2. The coastal farmland irrigation management method based on the smart agriculture control gateway according to claim 1 is characterized in that: The performing of linear regression analysis on the historical groundwater level data and the historical tidal data, and establishing a tidal force model according to the analysis results, comprises: Preprocessing the acquired historical groundwater level data and the historical tidal data; Draw a scatter plot based on the preprocessed historical groundwater level data and the historical tidal data, and obtain the correlation between the historical groundwater level data and the historical tidal data based on the scatter plot; An initial tidal force model is constructed according to the correlation, and the initial tidal force model is optimized by using the historical groundwater level data and the historical tidal data to obtain an optimized tidal force model.

3. The coastal farmland irrigation management method based on the smart agriculture control gateway according to claim 1 is characterized in that: The initial crop growth model constructed in the farmland in the target coastal area is trained based on the historical soil data, the historical meteorological data and the historical groundwater level data to obtain a trained crop growth model, including: Construct an initial crop growth model based on long short-term memory network; Preprocessing the historical soil data, the historical meteorological data, and the historical groundwater level data to obtain a training data set; The initial crop growth model is iteratively trained according to the training data set, and during the training process, the model parameters of the initial crop growth model are optimized by a back propagation algorithm to obtain a trained crop growth model.

4. The coastal farmland irrigation management method based on the smart agriculture control gateway as claimed in claim 3 is characterized in that: The preprocessing of the historical soil data, the historical meteorological data and the historical groundwater level data to obtain a training data set includes: Performing time alignment processing on the historical soil data, the historical meteorological data and the historical groundwater level data to obtain an initial data set; Extracting features from the initial data set to obtain target feature data, wherein the target features include soil moisture, soil temperature, precipitation, light intensity, and groundwater level; The target feature data is standardized to obtain the training data set.

5. The coastal farmland irrigation management method based on the smart agriculture control gateway according to claim 1 is characterized in that: The growth prediction indexes include crop water stress index, crop growth rate, soil moisture content, comprehensive index of meteorological conditions and crop growth stage; The control smart agriculture control gateway executes an irrigation plan that matches the growth prediction index, including: Determining the irrigation amount of the target coastal area farmland according to the crop water stress index, the crop growth rate and the soil moisture content; Determine the irrigation time of the farmland in the target coastal area according to the comprehensive index of meteorological conditions; determining the frequency and duration of irrigation according to the growth stage of the crop; An irrigation calculation is formulated based on the irrigation amount, the irrigation time, the irrigation frequency and the irrigation duration, and the smart agriculture control gateway is controlled to execute the irrigation plan.

6. A coastal farmland irrigation management device based on a smart agriculture control gateway, characterized in that: include: An acquisition module is used to respectively acquire historical soil data, historical groundwater level data, historical meteorological data, and historical tidal data of farmland in the target coastal area; An analysis module, used for performing linear regression analysis on the historical groundwater level data and the historical tidal data, and establishing a tidal force model according to the analysis results; A training module, used for training the initial crop growth model constructed in the farmland in the target coastal area based on the historical soil data, the historical meteorological data and the historical groundwater level data to obtain a trained crop growth model; A prediction module, used for inputting the acquired real-time tidal data into the tidal force model to obtain real-time groundwater level data during the irrigation management of the farmland in the target coastal area, and inputting the real-time groundwater level data, the acquired real-time soil data and the real-time meteorological data into the crop growth model to obtain growth prediction indicators of crops in the farmland in the target coastal area; The irrigation module is used to control the smart agriculture control gateway to execute an irrigation plan that matches the growth prediction index.

7. The coastal farmland irrigation management device based on the smart agriculture control gateway as claimed in claim 6 is characterized in that: The analysis module is specifically used for: Preprocessing the acquired historical groundwater level data and the historical tidal data; Draw a scatter plot based on the preprocessed historical groundwater level data and the historical tidal data, and obtain the correlation between the historical groundwater level data and the historical tidal data based on the scatter plot; An initial tidal force model is constructed according to the correlation, and the initial tidal force model is optimized by using the historical groundwater level data and the historical tidal data to obtain an optimized tidal force model.

8. The coastal farmland irrigation management device based on the smart agriculture control gateway as claimed in claim 6 is characterized in that: The training module is specifically used for: Construct an initial crop growth model based on long short-term memory network; Preprocessing the historical soil data, the historical meteorological data, and the historical groundwater level data to obtain a training data set; The initial crop growth model is iteratively trained according to the training data set, and during the training process, the model parameters of the initial crop growth model are optimized by a back propagation algorithm to obtain a trained crop growth model.

9. The coastal farmland irrigation management device based on the smart agriculture control gateway as claimed in claim 8, characterized in that: The training module is also used for: Performing time alignment processing on the historical soil data, the historical meteorological data and the historical groundwater level data to obtain an initial data set; Extracting features from the initial data set to obtain target feature data, wherein the target features include soil moisture, soil temperature, precipitation, light intensity, and groundwater level; The target feature data is standardized to obtain the training data set.

10. The coastal farmland irrigation management device based on the smart agriculture control gateway according to claim 6, characterized in that: The growth prediction indexes include crop water stress index, crop growth rate, soil moisture content, comprehensive index of meteorological conditions and crop growth stage; The irrigation module is specifically used for: Determining the irrigation amount of the target coastal area farmland according to the crop water stress index, the crop growth rate and the soil moisture content; Determine the irrigation time of the farmland in the target coastal area according to the comprehensive index of meteorological conditions; determining the frequency and duration of irrigation according to the growth stage of the crop; An irrigation calculation is formulated based on the irrigation amount, the irrigation time, the irrigation frequency and the irrigation duration, and the smart agriculture control gateway is controlled to execute the irrigation plan.

Images